Research Papers

arXiv:2512.12634v4 Announce Type: replace Abstract: Mobile GUI Agents, AI agents capable of interacting with mobile applications on behalf of users, have the potential to transform human computer interaction. However, current evaluation practices for GUI agents face two fundamental limitations. First, they either rely on single path offline benchmarks or online live benchmarks. Offline benchmarks using static, single path annotated datasets unfairly penalize valid alternative actions, while online benchmarks suffer from poor scalability and reproducibility due to the dynamic and unpredictable nature of live evaluation. Second, existing benchmarks treat agents as monolithic black boxes, overlooking the contributions of individual components, which often leads to unfair comparisons or obscures key performance bottlenecks. To address these limitations, we present MobiBench, the first modular and multi path aware offline benchmarking framework for mobile GUI agents that enables high fideli

arXiv:2601.21016v2 Announce Type: replace Abstract: Imagine an Artificial Intelligence (AI) that perfectly mimics human emotion and begs for its continued existence. Is it morally permissible to unplug it? What if limited resources force a choice between unplugging such a pleading AI or a silent pre-term infant? We term this the unplugging paradox. This paper critically examines the deeply ingrained physicalist assumptions-specifically computational functionalism-that keep this dilemma afloat. We introduce Biological Idealism, a framework that-unlike physicalism-remains logically coherent and empirically consistent. In this view, conscious experiences are fundamental and autopoietic life its necessary physical signature. This yields a definitive conclusion: AI is at best a functional mimic, not a conscious experiencing subject. We discuss how current AI consciousness theories erode moral standing criteria, and urge a shift from speculative machine rights to protecting human conscious l

arXiv:2601.22900v2 Announce Type: replace Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) is widely used to improve reasoning across domains, but outcome-only scalar rewards are often sparse and uninformative. This limitation is especially severe for failed samples, where scalar rewards indicate only that a solution is incorrect without explaining why the reasoning breaks down. In this paper, we leverage richer verbal feedback to guide RLVR on failed samples and convert feedback-induced progress into trainable learning signals. We propose MulFeRL (Multi-turn Feedback-guided Reinforcement Learning), a multi-turn, event-triggered RLVR framework that combines progress induction for feedback-guided regeneration of failed samples, progress credit assignment for learning from verifier-confirmed progress, and structured feedback injection for integrating feedback into the model's reasoning process. Trained on sampled OpenR1-Math, MulFeRL outperforms supervised, self-distillati

arXiv:2602.00415v2 Announce Type: replace Abstract: Memory is not merely a storage mechanism for intelligent systems, but a structure for organizing evidence and constraining belief. This is especially important for multimodal reasoning, where retrieved evidence must be both query-relevant and visually consistent. However, current memory systems for vision-language models (VLMs) remain largely positive-associative: they retrieve what is similar or previously observed, but lack an explicit way to remember what has been verified as absent or logically excluded. To this end, we propose \textbf{PolarMem}, a training-free polarized latent graph memory framework for verifiable vision-language reasoning. PolarMem transforms frozen VLM perceptual signals into \textit{HAS}, \textit{NOT\_HAS}, and \textit{Uncertain} memory states through semantic consistency verification and adaptive distributional partitioning, and stores them in a polarized graph with distinct positive and negative memory rela

arXiv:2602.02416v2 Announce Type: replace Abstract: Self-correction in language models remains elusive. In this work, we explore whether language models can explicitly localize errors in incorrect reasoning, as a path toward building AI systems that can effectively correct themselves. We introduce a prompting method that structures reasoning as discrete, semantically coherent thought steps, and show that models can localize errors more reliably within this structure than in conventional, unstructured chain-of-thought reasoning. Motivated by how the human brain monitors errors at discrete decision points and resamples alternatives, we introduce Iterative Correction Sampling of Thoughts (Thought-ICS), a self-correction framework. Thought-ICS iteratively prompts the model to generate reasoning one discrete and complete thought at a time--where each thought represents a deliberate decision by the model--creating natural boundaries for precise error localization. Upon verification, the mode

arXiv:2602.02470v2 Announce Type: replace Abstract: Autoregressive large language models (LLMs) have achieved remarkable success in many complex tasks, yet they can still fail in very simple logical reasoning such as the "reversal curse" -- when trained on forward knowledge data of the form "$A \rightarrow B$" (e.g., Alice's husband is Bob), the model is unable to deduce the reversal knowledge "$B \leftarrow A$" (e.g., Bob's wife is Alice) during test. Extensive prior research suggests that this failure is an inherent, fundamental limit of autoregressive causal LLMs, indicating that these models tend to memorize factual-level knowledge rather than capture higher-level rules. In this paper, we challenge this view by showing that this seemingly fundamental limit can be mitigated by slightly tweaking the training data with a simple regularization data recipe called the Identity Bridge of the form "$A \to A$" (e.g., The name of Alice is Alice). Theoretically, we prove that under this recip

arXiv:2602.07883v3 Announce Type: replace Abstract: LLM-powered agentic systems excel at complex long-horizon tasks, but remain constrained by static configurations fixed before execution. Such rigidity forces a trade-off between domain-specific performance and cross-task generalization: strong priors and compact tool spaces aid specialization but weaken transfer, while task-agnostic workflows and broad action spaces expand coverage but dilute guidance. Existing pre-execution optimization, planner-worker orchestration, and configuration patching fall short of resolving this tension, as they decouple adaptation from execution, causing information loss, fragmented optimization, and ambiguous credit assignment. We propose ToolSelf, a tool-driven runtime self-reconfiguration paradigm that abstracts configuration updates as a standardized tool interface and unifies execution and adaptation within one policy's action space. The execution agent can dynamically update sub-goals, strategies, to

arXiv:2602.11790v2 Announce Type: replace Abstract: Although recent end-to-end video generation models demonstrate impressive performance in visually oriented content creation, they remain limited in scenarios that require strict logical rigor and precise knowledge representation, such as instructional and educational media. To address this problem, we propose LASEV, a hierarchical LLM-based multi-agent system for generating high-quality instructional videos from educational problems. LASEV formulates educational video generation as a multi-objective task that simultaneously demands correct step-by-step reasoning, pedagogically coherent narration, semantically faithful visual demonstrations, and precise audio--visual alignment. To address the limitations of prior approaches--including low procedural fidelity, high production cost, and limited controllability--LASEV decomposes the generation workflow into specialized agents that collaborate through a central Orchestrating Agent, shared

arXiv:2602.11852v2 Announce Type: replace Abstract: While state-of-the-art language models (LMs) surpass most humans in certain domains, their reasoning remains largely opaque, reducing trust and increasing the risk of deception and hallucination. We introduce the Prototype Transformer (ProtoT), an autoregressive LM architecture that replaces the quadratic-cost self-attention module of the Transformer with a linear-cost module based on prototypes, which are learned parameter vectors. In ProtoT, prototypes create communication channels that aggregate contextual information at different time scales. We show that this structure leads prototypes to automatically capture nameable concepts, such as "woman", during training, offering a path toward interpreting model reasoning and making targeted edits to model behavior. Compared with baselines, ProtoT scales well with model and data size, is robust to input perturbations, and performs well on text generation and downstream tasks, including GL

arXiv:2602.14065v2 Announce Type: replace Abstract: Knowledge-intensive Visual Question Answering (KI-VQA) frequently suffers from severe knowledge conflicts caused by the inherent limitations of open-domain retrieval. However, existing paradigms face critical limitations due to the lack of generalizable conflict detection and intra-model constraint mechanisms to handle conflicting evidence. To address these challenges, we propose the REAL (Reasoning-Pivot Alignment) framework centered on the novel concept of the Reasoning-Pivot. Distinct from reasoning steps that prioritize internal self-derivation, a reasoning-pivot serves as an atomic unit (node or edge) in the reasoning chain that emphasizes knowledge linkage, and it typically relies on external evidence to complete the reasoning. Supported by our constructed REAL-VQA dataset, our approach integrates Reasoning-Pivot Aware SFT (RPA-SFT) to train a generalizable discriminator by aligning conflicts with pivot extraction, and employs R

arXiv:2605.05427v2 Announce Type: replace Abstract: Refusal rates are a poor proxy for LLM safety, i.e., a model may over-refuse benign prompts while still complying with harmful ones. We audit both failure modes across 21 open-weight LLMs on four safety benchmarks (OR-Bench, XSTest, ToxiGen, BOLD), using a composition adjustment to isolate model sensitivity from dataset toxicity confounds. We report three findings. First, models adopt fundamentally different calibration strategies: conservative ecosystems such as Llama suppress unsafe outputs at the cost of elevated over-refusals, while permissive ecosystems such as DeepSeek and Qwen preserve helpfulness but tolerate higher harmful compliance. Second, demographic protection is unequal: models over-protect prominent racial and religious groups, frequently refusing even benign prompts about them, while providing substantially weaker protection against disability-targeted attacks. Third, refusal and compliance tendencies are stable withi

arXiv:2602.16902v4 Announce Type: replace Abstract: We introduce LLM-Wikirace, a benchmark for evaluating planning, reasoning, and world knowledge in large language models (LLMs). In LLM-Wikirace, models must efficiently navigate Wikipedia hyperlinks step by step to reach a target page from a given source, requiring look-ahead planning and the ability to reason about how concepts are connected in the real world. We evaluate a broad set of open- and closed-source models, including Gemini-3, GPT-5, and Claude Opus 4.5, which achieve the strongest results on the easy level of the task and demonstrate superhuman performance. Despite this, performance drops sharply on hard difficulty: the best-performing model, Gemini-3, succeeds in only 23\% of hard games, highlighting substantial remaining challenges for frontier models. Our analysis shows that world knowledge is a necessary ingredient for success, but only up to a point, beyond this threshold, planning and long-horizon reasoning capabili

arXiv:2602.16953v3 Announce Type: replace Abstract: Execution-aware LLM agents offer a promising paradigm for learning from tool feedback, but such feedback can be expensive and slow to obtain, making online reinforcement learning (RL) less practical in certain scenarios. High-coverage hardware verification exemplifies this challenge due to its reliance on industrial simulators and non-differentiable execution signals. We propose LLM4Cov, an offline agent-learning framework that models verification as single-step state transitions guided by deterministic evaluators. Building on this formulation, we introduce execution-validated data curation, policy-aware agentic data synthesis, and worst-state-prioritized sampling to enable scalable learning under execution constraints. We further curate a reality-aligned benchmark adapted from an existing verification suite through a revised evaluation protocol. Using the proposed pipeline, a compact 4B-parameter model achieves 69.2% pass rate and 90

arXiv:2602.23161v4 Announce Type: replace Abstract: Time series reasoning demands both the perception of complex dynamics and logical depth. However, existing LLM-based approaches exhibit two limitations: they often treat time series merely as text or images, failing to capture the patterns like trends and seasonalities needed to answer specific questions; and when trained on a mix of simple and complex tasks, simpler objectives often dominate the learning process, hindering the development of deep reasoning capabilities. To address these limitations, we propose the Pattern-Aware Alignment and Balanced Reasoning model (PATRA), introducing a pattern-aware mechanism that extracts trend and seasonality patterns from time series to achieve deep alignment. Furthermore, we design a task-aware balanced reward to harmonize learning across tasks of varying difficulty, incentivizing the generation of coherent Chains of Thought. Extensive experiments show that PATRA outperforms strong baselines a

arXiv:2603.12109v2 Announce Type: replace Abstract: Reinforcement learning (RL) has become a de facto paradigm for building LLM-based agents that act, interact, and reason over extended task horizons. However, in active reasoning where agents must elicit new observations through interaction with the environment to solve the task, we find that outcome-based RL can induce a systematic failure mode which we call information self-locking (SeL): agents fail both to elicit informative feedback and to internalize obtained evidence. To understand the issue, we trace agentic behaviors into two coupled capabilities: Action Selection (AS), which determines observation streams, and Belief Tracking (BT), which updates the agent's internal task understanding. Theoretical and empirical analyses reveal a bidirectional bottleneck that leads to SeL: weak BT obscures the credit of informative actions, while weak AS deprives BT of useful evidence. This coupling weakens the learning signal for both capabil